LOCUS       VTR91519.1               873 aa    PRT              BCT 03-FEB-2020
DEFINITION  Gemmata massiliana Uncharacterized protein OS=Candidatus
            Entotheonella sp. TSY2 GN=ETSY2_22110 PE=4 SV=1 protein.
ACCESSION   LR593886-820
PROTEIN_ID  VTR91519.1
SOURCE      Gemmata massiliana
  ORGANISM  Gemmata massiliana
            Bacteria; Planctomycetes; Planctomycetia; Gemmatales; Gemmataceae;
            Gemmata.
REFERENCE   1
  AUTHORS   
  CONSRTM   Science for Life Laboratories
  JOURNAL   Submitted (14-MAY-2019) to the INSDC. DEPARTMENT OF CELL AND
            MOLECULAR BIOLOGY, Uppsala University, Molecular Evolution,
            Biomedicinskt centrum (BMC), Husargatan 3, 752 37 Uppsala, Sweden
FEATURES             Qualifiers
     source          /organism="Gemmata massiliana"
                     /chromosome="1"
                     /isolate="Soil9"
                     /mol_type="genomic DNA"
                     /isolation_source="soil"
                     /db_xref="taxon:1210884"
     protein         /locus_tag="SOIL9_61950"
                     /note="BLAST_uniprot:hit_1 ;
                     ACCESSION=tr|W4M6L4|W4M6L4_9DELT ;
                     ALN/Q_length_ratio=0.537 ; DESCRIPTION=Uncharacterized
                     protein OS=Candidatus Entotheonella sp. TSY2
                     GN=ETSY2_22110 PE=4 SV=1 ; EVALUE=5e-50 ;
                     Q/S_length_ratio=1.267"
                     /note="BLAST_uniprot:hit_2 ;
                     ACCESSION=tr|W4LK30|W4LK30_9DELT ;
                     ALN/Q_length_ratio=0.549 ; DESCRIPTION=Uncharacterized
                     protein OS=Candidatus Entotheonella sp. TSY1
                     GN=ETSY1_21580 PE=4 SV=1 ; EVALUE=5e-48 ;
                     Q/S_length_ratio=1.267"
BEGIN
        1 MNATALAPEP TLTGRTRDVL KRAGNPFRNY FARNPDDEVC ARFHVPELFA AERDLLHAII
       61 DLYRYDPQTH SEVVPILGNK GAGKTHLLHS IKHGVGGQWQ LLVTPGVYQR DSDFLEYLLF
      121 QIIDTLLGGG KQKGVRPLDF IGDQLVRRQL GVALRELSDE EKVELFPPPG LGRWARRLGL
      181 GTQQARERAE WLAENLSGYS NFARMPTPIA QALTDAGLTP QKAFDLVCTH IQKNEAHNTA
      241 GLMRRHIFQG FAKAALLRDE SELANFLTYG FAELEFHVRP TRQDLVLALF KVLTEVFRSL
      301 KTPVVVAFDQ LEDLLLARRT DDAHRTAEAF FAGIVQVMHQ IDGLCFLIFA ERGLWNRFVP
      361 SLDGYIQDRL NNPVHVPKHG TVKAIRLEAP PADLVRRVVE ARLRSCLGEL PAGESVSEIF
      421 PFVDEQITRI ARTEPTLRDM LQQFRHLFDH VVYGPDDAQA PVARVSEPTP VKAVEVELIQ
      481 PDAAPELPAG RFDVTAEIAA MPALPAPVIE PKLPELPVSY DPVSRIAALL GRDEDDVLPP
      541 LPTLTIKHVE VIEAPAEEPP VAEVVSPAPL LMLPPAVTDD VPMAVAVDLE EIVEESITSS
      601 ELVVEVQEPP ALPVVQAEAP TVVAAAPEVP AVAPFPSAVP ANVSPATVVK PAVSVAATAP
      661 AVARDSHAAL VELWEQEQRA ARRKLEPEGA LTGATRELQA GLGAFLSVCH EHGVKVGPWR
      721 LQHVVNEWSY GEHPTYGVVT IAHWACKDAQ PWRMGLGLFL ARGAGKPKDL EVKLAVLDTE
      781 PAVVDLLVLL RPEDDIATTG KSKTLLQDAE RRGKHTRLEP VSLDGFAQMY AFPRWLAAVR
      841 ESLPEGAPLP NLADIIQEKG EKLLEQVCMP VQG
//